MCPcopy Create free account

hub / github.com/3DTopia/DynamicCity / types & classes

Types & classes41 in github.com/3DTopia/DynamicCity

⨍ Functions 220◇ Types & classes 41
↓ 2 callersClassAttention
dynamic_city/utils/attention_utils.py:6
↓ 2 callersClassDiT
Diffusion model with a Transformer backbone.
dynamic_city/diffusion/models.py:76
↓ 2 callersClassVAETrainer
dynamic_city/trainer/vae_trainer.py:28
↓ 2 callersClassVoxelEncoder
dynamic_city/vae/encoder_blocks.py:8
↓ 1 callersClassCmdCondEmbedder
dynamic_city/diffusion/embedders.py:137
↓ 1 callersClassCrossAttention
dynamic_city/utils/attention_utils.py:32
↓ 1 callersClassDiTBlock
A DiT block with adaptive layer norm zero (adaLN-Zero) conditioning.
dynamic_city/diffusion/models.py:24
↓ 1 callersClassDiTTrainer
dynamic_city/trainer/dit_trainer.py:23
↓ 1 callersClassDynamicCityAE
Main class for the DynamicCity autoencoder. Enables easy switching between different encoders and decoders and optional VAE.
dynamic_city/vae/vae.py:9
↓ 1 callersClassFinalLayer
The final layer of DiT.
dynamic_city/diffusion/models.py:55
↓ 1 callersClassGaussianDiffusion
Utilities for training and sampling diffusion models. Original ported from this codebase: https://github.com/hojonathanho/diffusion/blob/
dynamic_city/diffusion/gaussian_diffusion.py:144
↓ 1 callersClassHexCondEmbedder
dynamic_city/diffusion/embedders.py:106
↓ 1 callersClassHexPlaneVAE
dynamic_city/vae/vae.py:52
↓ 1 callersClassHexplaneConvBlock
dynamic_city/vae/decoder_blocks.py:9
↓ 1 callersClassLayoutCondEmbedder
dynamic_city/diffusion/embedders.py:112
↓ 1 callersClassLossSecondMomentResampler
dynamic_city/diffusion/timestep_sampler.py:120
↓ 1 callersClassMetrics
dynamic_city/utils/metrics.py:8
↓ 1 callersClassPlaneDownsampler
dynamic_city/vae/encoder_blocks.py:52
↓ 1 callersClassPlaneUpsampler
dynamic_city/vae/decoder_blocks.py:43
↓ 1 callersClassSpacedDiffusion
A diffusion process which can skip steps in a base diffusion process. :param use_timesteps: a collection (sequence or set) of timesteps from
dynamic_city/diffusion/respace.py:65
↓ 1 callersClassTimestepEmbedder
Embeds scalar timesteps into vector representations.
dynamic_city/diffusion/embedders.py:8
↓ 1 callersClassTrajCondEmbedder
dynamic_city/diffusion/embedders.py:126
↓ 1 callersClassTransformer
Simple Transformer block with flash attention.
dynamic_city/vae/encoder_blocks.py:72
↓ 1 callersClassUniformSampler
dynamic_city/diffusion/timestep_sampler.py:62
↓ 1 callersClassVoxelDecoderBlock
dynamic_city/vae/decoder_blocks.py:60
↓ 1 callersClass_WrappedModel
dynamic_city/diffusion/respace.py:117
ClassCarlaSCHexPlaneDataset
dynamic_city/dataset/carlasc.py:40
ClassCarlaSCOccSequenceDataset
dynamic_city/dataset/carlasc.py:10
ClassCommand
dynamic_city/utils/data_utils.py:57
ClassConvDecoder
dynamic_city/vae/decoder.py:36
ClassDecoderBase
dynamic_city/vae/decoder.py:9
ClassEmbedder
dynamic_city/diffusion/embedders.py:49
ClassEncoderBase
dynamic_city/vae/encoder.py:12
ClassHexPlaneDataset
dynamic_city/dataset/hexplane_dataset.py:11
ClassLossAwareSampler
dynamic_city/diffusion/timestep_sampler.py:71
ClassLossType
dynamic_city/diffusion/gaussian_diffusion.py:46
ClassModelMeanType
Which type of output the model predicts.
dynamic_city/diffusion/gaussian_diffusion.py:23
ClassModelVarType
What is used as the model's output variance. The LEARNED_RANGE option has been added to allow the model to predict values between FIXED_S
dynamic_city/diffusion/gaussian_diffusion.py:33
ClassOccSequenceDataset
dynamic_city/dataset/occ_sequence_dataset.py:10
ClassScheduleSampler
A distribution over timesteps in the diffusion process, intended to reduce variance of the objective. By default, samplers perform unbias
dynamic_city/diffusion/timestep_sampler.py:27
ClassTrEncoder
dynamic_city/vae/encoder.py:72